{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y3I7JR3BHLPX557T32IPUUHZAN","short_pith_number":"pith:Y3I7JR3B","schema_version":"1.0","canonical_sha256":"c6d1f4c7613adf7ef7f3de90fa50f9035aa3fba47fbe01d5cc127e33f3fd7de0","source":{"kind":"arxiv","id":"2608.00009","version":1},"attestation_state":"computed","paper":{"title":"AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Cherif","submitted_at":"2026-06-16T08:27:18Z","abstract_excerpt":"Long-term memory remains a critical bottleneck for conversational AI agents, whose finite context windows cannot support coherent recall across thousands of turns. We present AgentMemBench, a unified, reproducible benchmark evaluating five memory management strategies under identical conditions: in-context windowing (ICW), external key-value store (EKV), graph-based episodic memory (GEM), compression-based summarisation (CBS), and web-augmented memory (WAM). All are assessed across three public datasets covering long-term multi-session dialogue (LoCoMo), task-oriented document grounding (Multi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.00009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T08:27:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"048671dd1253507989fd1dc3e86ef75a1ae406c14536102406423c0f82551089","abstract_canon_sha256":"437659d9c3ea968b8bef536b313b833dcd0feb478f5b99c8b6a0418fa61744b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:31:37.719540Z","signature_b64":"zqbOl1e5MB12OzadQhieFz5dKxlIrGBjX3cW+nSwYfgvD/MygqT8pVNHyZylx3+s1o30MLhWPFQbottxSKXLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d1f4c7613adf7ef7f3de90fa50f9035aa3fba47fbe01d5cc127e33f3fd7de0","last_reissued_at":"2026-08-04T00:31:37.718007Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:31:37.718007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Cherif","submitted_at":"2026-06-16T08:27:18Z","abstract_excerpt":"Long-term memory remains a critical bottleneck for conversational AI agents, whose finite context windows cannot support coherent recall across thousands of turns. We present AgentMemBench, a unified, reproducible benchmark evaluating five memory management strategies under identical conditions: in-context windowing (ICW), external key-value store (EKV), graph-based episodic memory (GEM), compression-based summarisation (CBS), and web-augmented memory (WAM). All are assessed across three public datasets covering long-term multi-session dialogue (LoCoMo), task-oriented document grounding (Multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00009","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.00009/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.00009","created_at":"2026-08-04T00:31:37.719012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00009v1","created_at":"2026-08-04T00:31:37.719012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00009","created_at":"2026-08-04T00:31:37.719012+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3I7JR3BHLPX","created_at":"2026-08-04T00:31:37.719012+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3I7JR3BHLPX557T","created_at":"2026-08-04T00:31:37.719012+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3I7JR3B","created_at":"2026-08-04T00:31:37.719012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN","json":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN.json","graph_json":"https://pith.science/api/pith-number/Y3I7JR3BHLPX557T32IPUUHZAN/graph.json","events_json":"https://pith.science/api/pith-number/Y3I7JR3BHLPX557T32IPUUHZAN/events.json","paper":"https://pith.science/paper/Y3I7JR3B"},"agent_actions":{"view_html":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN","download_json":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN.json","view_paper":"https://pith.science/paper/Y3I7JR3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00009&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3I7JR3BHLPX557T32IPUUHZAN/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3I7JR3BHLPX557T32IPUUHZAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN/action/storage_attestation","attest_author":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN/action/author_attestation","sign_citation":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN/action/citation_signature","submit_replication":"https://pith.science/pith/Y3I7JR3BHLPX557T32IPUUHZAN/action/replication_record"}},"created_at":"2026-08-04T00:31:37.719012+00:00","updated_at":"2026-08-04T00:31:37.719012+00:00"}